Autonomously Generating Annotated Training Data for 6D Object Pose Estimation
Keywords
Loading...
Authors
Issue Date
2020-10-26
Language
en
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Recently developed deep neural networks achieved state-of-the-art results in the subject of 6D object
pose estimation for robot manipulation. However, those supervised deep learning methods
require expensive annotated training data. Current methods for reducing those costs frequently
use synthetic data from simulations, but they rely on expert knowledge and suffer from the reality
gap when shifting to the real world. The present research project is a proof of concept for
autonomously generating annotated training data for 6D object pose estimation, which addresses
both the subject of cost reduction and the applicability to the real world task at hand. A training
data set is generated for a given grasping task with an industrial robot arm at its indented workstation.
Additionally, the data is autonomously annotated via background subtraction and point
cloud stitching. A state-of-the-art neural network for 6D object pose estimation is trained with
the generated data set and a grasping experiment is conducted in order to evaluate the quality of
the pose estimation. The proposed concept outperforms related work with respect to the grasping
success rate, while circumventing the reality gap, removing annotation cost, and avoiding expert
labor. Thereby, it is demonstrated that the data required to train a 6D object pose estimation
neural network can be generated and autonomously annotated with sufficient quality within the
workstation of an industrial robot arm for its intended task.
Description
Citation
Supervisor
Faculty
Faculteit der Sociale Wetenschappen